Microstructural Materials Design Via Deep Adversarial Learning Methodology

Abstract

Identifying the key microstructure representations is crucial for Computational Materials Design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for microstructural materials design. Some MCR approaches are not applicable for microstructural materials design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures 1 . Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex ma- * These authors contributed equally to this work. terial microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for microstructural materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural materials design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

Deep Generative Design: Integration of Topology Optimization and Generative Models

“…Fourth, deep learning application on material design has been developed because of the direct relationship between the density of element in material structure and pixels of images, resulting to easy transformation of the domain from the material structures to images. Yang et al [14] obtain optimal microstructure by using Bayesian optimization framework where the microstructure is mapped into low-dimensional latent variables by using GAN. Cang et al [13] propose a feature extraction method to convert the microstructure to low-dimensional design space through a convolutional deep belief network.…”

“…The generative model is an algorithm for constructing a generator that learns the probability distribution of training data and generates new data based on learned probability distribution. In particular, variational autoencoder (VAE) and generative adversarial network (GAN) are popular generative models used in design optimization, where high-dimensional design variables are encoded in low-dimensional design space [13,14]. In addition, these models are utilized in the design exploration and shape parameterization [8,9].The use of generative model to produce engineering designs directly is limited [23].…”

Microstructure synthesis using style-based generative adversarial networks

“…Large deep learning models require a big amount of data and GAN models [3] were initially developed to create artificial data for training neural networks. Later GAN was used for material design [15]. Authors of the paper aim to develop a model that will be able to create a microstructure by the given properties.…”

Rethinking interphase representations for modeling viscoelastic properties for polymer nanocomposites

“…In proposing the next candidate point, several criteria have been used. For instance, [32] utilizes Expected Improvement (EI) while Li and Yang et al [42,43] applies the GP-Hedge criteria which combines three scores --EI, lower confidence bound (LCB) and probability of improvement (PI). In this work, EI is utilized to propose the next candidate point +1 = ( + , + ) to explore.…”